{"id":"https://openalex.org/W2790781626","doi":"https://doi.org/10.1109/vcip.2017.8305157","title":"Image retrieval by dense caption reasoning","display_name":"Image retrieval by dense caption reasoning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2790781626","doi":"https://doi.org/10.1109/vcip.2017.8305157","mag":"2790781626"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2017.8305157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2017.8305157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112233597","display_name":"Xinru Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinru Wei","raw_affiliation_strings":["School of Communication and Information Engineering, BUPT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075315261","display_name":"Yonggang Qi","orcid":"https://orcid.org/0000-0001-8280-3541"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonggang Qi","raw_affiliation_strings":["School of Communication and Information Engineering, BUPT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361857","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-4365-4165"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["School of Communication and Information Engineering, BUPT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100453075","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0002-5669-9354"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Liu","raw_affiliation_strings":["School of Communication and Information Engineering, BUPT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.3695,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.71062271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8018860816955566},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.77839195728302},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.7689914703369141},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.6409923434257507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6330337524414062},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5559400320053101},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.553296685218811},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5269226431846619},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5230339765548706},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.4935852289199829},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.46274664998054504},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.4417746067047119},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4317224621772766},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.417986124753952},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3236326575279236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08142727613449097},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.07350635528564453},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.06536898016929626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8018860816955566},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.77839195728302},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.7689914703369141},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.6409923434257507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330337524414062},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5559400320053101},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.553296685218811},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5269226431846619},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5230339765548706},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.4935852289199829},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.46274664998054504},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.4417746067047119},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4317224621772766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.417986124753952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3236326575279236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08142727613449097},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.07350635528564453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.06536898016929626},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip.2017.8305157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2017.8305157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1566018662","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W2031489346","https://openalex.org/W2077069816","https://openalex.org/W2090042335","https://openalex.org/W2097018403","https://openalex.org/W2134168908","https://openalex.org/W2147238549","https://openalex.org/W2151103935","https://openalex.org/W2161969291","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2951183276","https://openalex.org/W2963758027","https://openalex.org/W4232730838","https://openalex.org/W6633661181","https://openalex.org/W6674642818"],"related_works":["https://openalex.org/W2123147980","https://openalex.org/W2066590080","https://openalex.org/W2076842684","https://openalex.org/W2918350319","https://openalex.org/W2513891871","https://openalex.org/W1539573266","https://openalex.org/W4387423606","https://openalex.org/W2187873862","https://openalex.org/W3101846449","https://openalex.org/W2396850383"],"abstract_inverted_index":{"Humans":[0],"tend":[1],"to":[2,20,44],"understand":[3],"image":[4,34,38,60,86],"scene":[5,67],"by":[6,36,71],"recognizing":[7],"visual":[8],"elements,":[9],"then":[10],"conjecturing":[11],"and":[12,66,92],"inferring":[13],"based":[14],"on":[15,80],"them,":[16],"hence":[17],"are":[18],"able":[19],"search":[21],"relevant":[22],"images.":[23,52],"In":[24],"this":[25],"paper,":[26],"we":[27,54],"concern":[28],"about":[29],"the":[30,45,56,90],"problem":[31,57],"of":[32,47,58,94],"complex":[33,59],"retrieval":[35,61,87],"reasoning":[37],"dense":[39,64],"captions,":[40],"which":[41],"is":[42],"similar":[43],"way":[46],"human":[48],"perception":[49],"for":[50,76],"searching":[51],"Specifically,":[53],"transform":[55],"into":[62],"a":[63,81],"captioning":[65],"graph":[68],"matching":[69],"issue":[70],"using":[72],"structured":[73],"language":[74],"descriptions":[75],"retrieval.":[77],"Experimental":[78],"results":[79],"novel":[82],"proposed":[83],"large-scale":[84],"content-based":[85],"dataset":[88],"demonstrate":[89],"rationality":[91],"effectiveness":[93],"our":[95],"method.":[96]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}